HomeProjectsArticlesPK BoardAbout
Explore Projects

Orca

Active
GitHub TypeScript MIT

Description

orca is a developer-facing AI agent platform providing RAG, inference, hosted tooling and an end-to-end capability stack.

Key Features

  • End-to-end platform — RAG, tools, hosted deployment in one
  • Agent framework — built-in orchestration, memory and tool calling
  • Multi-model routing — routes each task to the optimal model
  • Observability — full tracing, call stats and cost analytics
  • Team collaboration — multi-user development of agent projects
  • Enterprise SLA — multi-region deployment, RBAC and compliance

Use Cases

💡 Rapidly developing and shipping AI agent apps on one platform
💡 Private deployment of AI agents for enterprises
💡 Letting non-AI teams configure production-ready RAG and agents
💡 A unified infra for agent evaluation and benchmarks

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (60.1k stars)
  • • Permissive open-source license (MIT)

⚠️ Limitations

  • • High issue backlog (5.1k open issues)

Tags

ai-platform agent cloud inference rag

Categories

🤖 Agent Framework ⚡ Agent Tools

Quick Start

npm install -g @orca/cli
orca login
orca init my-agent
orca deploy
Visit GitHub Visit Website

Related Projects

exo

47.2k · Python
Active A+

exo is a framework that pools many consumer-grade devices into a distributed LLM inference cluster, turning Macs, PCs and Linux boxes into one GPU pool.

distributedllmcluster +2
  • · Consumer-device cluster — every node is a desktop or laptop, no datacenter GPUs needed
  • · P2P auto-discovery — devices on the same LAN join the cluster automatically
  • · Dynamic partitioning — models are split by layers / tensors across nodes
View full details → View on GitHub